Merge pull request #3 from jonasschultheiss/emustafa/recom

Emustafa/recom

recommander/data_gen.ipynb

@@ -0,0 +1,133 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Art\n",
+    "Sports\n",
+    "Politics\n",
+    "Books\n",
+    "Movies\n",
+    "Technology\n",
+    "Fashion\n",
+    "Outdoor Activities\n",
+    "Pets\n",
+    "Familiy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import random\n",
+    "import requests\n",
+    "import json\n",
+    "import credentials"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def generate_random_entries(N):\n",
+    "    entries = []\n",
+    "    for _ in range(N):\n",
+    "        entry = {category: random.randint(1, 5) for category in categories}\n",
+    "        entries.append(entry)\n",
+    "    return entries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mockaroo_url = '\thttps://api.mockaroo.com/api/generate.csv'\n",
+    "# API key\n",
+    "num_rows_to_generate = 300  # Max 1000 for the free version of the API"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def post_request():\n",
+    "\n",
+    "    url = url = mockaroo_url + '?key=' + credentials.mockaroo_key + '&count=' + str(num_rows_to_generate)\n",
+    "\n",
+    "\n",
+    "    with open('schema.json', 'r') as datafile:\n",
+    "        fields = json.load(datafile)\n",
+    "    # Make a post call to the URL\n",
+    "    # Body of the post request is the schema definition of the output expected\n",
+    "    response = requests.post(url=url, json=fields)\n",
+    "\n",
+    "    # Write the output to a file (output.json)\n",
+    "    with open('output.csv', 'w') as outfile:\n",
+    "        outfile.write(response.text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "post_request()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'Art': 1, 'Sports': 5, 'Politics': 5, 'Books': 3, 'Movies': 2, 'Technology': 1, 'Fashion': 3, 'Outdoor Activities': 5, 'Pets': 4, 'Family': 1}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(random_entries[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "bhack",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}